Hi Adrian, ... hadn't you exported the same disks in both servers at some point in time? Maybe Andy is referring to that. Fabrizio On 10/11/2013 08:20 AM, Adrian Sevcenco wrote: > On 10/11/2013 12:57 AM, Andrew Hanushevsky wrote: >> Hi Adrian, > Hi! > >> Looks to me that the double space problem comes from the fact that >> /storage01 has been included twice in the configuration. Additionally, > in configuration i have nothing twice .. > >> it would appear that /storage02 and /storage03 have not been included in >> the configuration. Could you send me your config file? I suspect that >> this is the problem here. > all config files attached .. xrootd.xrootd.cf is (re) created based on > system.cnf file > > Thanks for helping me with this! > Adrian > >> >> Andy >> >> -----Original Message----- From: Adrian Sevcenco >> Sent: Thursday, October 10, 2013 12:04 AM >> To: Andrew Hanushevsky >> Cc: [log in to unmask] >> Subject: Re: xrootd :: server 3.3.2 bug :: double size reporting >> >> On 10/10/2013 08:52 AM, Adrian Sevcenco wrote: >>> On 10/10/2013 03:26 AM, Andrew Hanushevsky wrote: >>>> Hi Adrian, >>> Hi! >>> >>>> Could you try to use xrdfs (the new client based xrd replacement) to see >>>> what you get there? >>> it reports double space also: >>> aliprod@storage03: ~ $ xrdfs localhost statvfs / >>> Path: / >>> Nodes with RW space: 1 >>> Size of RW space (MB): 7978 >> this is not so informative it seems .. it reports only ~8 Gb space! >> >> aliprod@storage03: ~ $ xrdfs localhost query space / >> oss.cgroup=public&oss.space=86636386320384&oss.free=11850958060&oss.maxf=2089872388&oss.used=10885940771&oss.quota=-1 >> >> >> aliprod@storage03: ~ $ xrdfs localhost query stats total >> <statistics tod="1381388316" ver="v3.3.2" >> src="storage03.spacescience.ro:1094" tos="1381231940" pgm="xrootd" >> ins="anon" pid="12987" site=""><stats >> id="info"><host>storage03.spacescience.ro</host><port>1094</port><name>anon</name></stats><stats >> >> id="buff"><reqs>105006</reqs><mem>137090048</mem><buffs>180</buffs><adj>0</adj></stats><stats >> >> id="link"><num>10</num><maxn>73</maxn><tot>28885</tot><in>18096047509</in><out>1510999236517</out><ctime>1995692</ctime><tmo>45893</tmo><stall>0</stall><sfps>0</sfps></stats><stats >> >> id="poll"><att>10</att><en>49466</en><ev>45888</ev><int>0</int></stats><stats >> >> id="proc"><usr><s>40</s><u>428853</u></usr><sys><s>2509</s><u>239537</u></sys></stats><stats >> >> id="xrootd"><num>28884</num><ops><open>40772</open><rf>0</rf><rd>19695905</rd><pr>0</pr><rv>931313</rv><rs>10051282</rs><wr>4169</wr><sync>0</sync><getf>0</getf><putf>0</putf><misc>86049</misc></ops><aio><num>0</num><max>0</max><rej>0</rej></aio><err>201</err><rdr>0</rdr><dly>0</dly><lgn><num>28882</num><af>0</af><au>28880</au><ua>0</ua></lgn></stats><stats >> >> id="ofs"><role>server</role><opr>3</opr><opw>0</opw><opp>0</opp><ups>0</ups><han>3</han><rdr>0</rdr><bxq>0</bxq><rep>0</rep><err>0</err><dly>0</dly><sok>0</sok><ser>0</ser><tpc><grnt>0</grnt><deny>0</deny><err>0</err><exp>0</exp></tpc></stats><stats >> >> id="oss" v="2"><paths>2<stats >> id="0"><lp>"/"</lp><rp>"/storage01/xrdnamespace/home/aliprod/data/"</rp><tot>13959964628</tot><free>7213124</free><ino>1772814336</ino><ifr>1769450005</ifr></stats><stats >> >> id="1"><lp>"/"</lp><rp>"/storage01/xrdnamespace/home/aliprod/data/"</rp><tot>13959964628</tot><free>7213124</free><ino>1772814336</ino><ifr>1769450005</ifr></stats></paths><space>2<stats >> >> id="0"><name>public</name><tot>84605846016</tot><free>2010157</free><maxf>443841</maxf><fsn>6</fsn><usg>10693215</usg></stats></space></stats><stats >> >> id="sched"><jobs>78587</jobs><inq>0</inq><maxinq>2</maxinq><threads>28</threads><idle>27</idle><tcr>28</tcr><tde>0</tde><tlimr>0</tlimr></stats><stats >> >> id="sgen"><as>1</as><et>9</et><toe>1381388316</toe></stats></statistics> >> >> the problem is more clear in this output.. >> >> Thanks! >> Adrian >> >> >> >> >>> Utilization of RW space (%): c >>> Nodes with staging space: 0 >>> Size of staging space (MB): 0 >>> Utilization of staging space (%): >>> >>> >>> Thanks! >>> Adrian >>> >>> >>>> >>>> Andy >>>> >>>> -----Original Message----- From: Adrian Sevcenco >>>> Sent: Tuesday, October 08, 2013 4:58 AM >>>> To: [log in to unmask] >>>> Subject: xrootd :: server 3.3.2 bug :: double size reporting >>>> >>>> Hi! I have a nagging problem with the reporting of size in xrootd: >>>> >>>> aliprod@storage03: ~ $ echo exit | ~/xrdserver/bin/xrd localhost >>>> queryspace / - >>>> Disk space approximations (MB): >>>> Total : 82622896 >>>> Free : 39192 >>>> Used : 0 >>>> Largest chunk : 7190 >>>> >>>> aliprod@storage03: ~ $ df -B M | grep storage >>>> /dev/sdc1 13632778M 13626433M 6346M 100% /storage01 >>>> /dev/sdc2 13632778M 13625588M 7191M 100% /storage02 >>>> /dev/sdc3 14045893M 14039832M 6061M 100% /storage03 >>>> >>>> aliprod@storage03: ~ $ df -BM | grep storage | awk 'BEGIN {total=0} >>>> {gsub("M",""); total+= $2;} END {print total}' >>>> 41311449 >>>> >>>> given that the problem is the queryspace result, i imagine that is a >>>> problem internal to xrd. ( it seems that the 3.2.6 version is ok.)(this >>>> are ALICE packaged versions) >>>> >>>> Any idea about the problem and how can i investigate more? >>>> Thanks a lot! >>>> Adrian >>>> >>>> >>>> ######################################################################## >>>> Use REPLY-ALL to reply to list >>>> >>>> To unsubscribe from the XROOTD-L list, click the following link: >>>> https://listserv.slac.stanford.edu/cgi-bin/wa?SUBED1=XROOTD-L&A=1 >>> >>> >>> >>> ######################################################################## >>> Use REPLY-ALL to reply to list >>> >>> To unsubscribe from the XROOTD-L list, click the following link: >>> https://listserv.slac.stanford.edu/cgi-bin/wa?SUBED1=XROOTD-L&A=1 >>> >> >> > > > ######################################################################## > Use REPLY-ALL to reply to list > > To unsubscribe from the XROOTD-L list, click the following link: > https://listserv.slac.stanford.edu/cgi-bin/wa?SUBED1=XROOTD-L&A=1 > ######################################################################## Use REPLY-ALL to reply to list To unsubscribe from the XROOTD-L list, click the following link: https://listserv.slac.stanford.edu/cgi-bin/wa?SUBED1=XROOTD-L&A=1